We present TrialsSummarizer, a system that aims to automatically summarize evidence presented in the set of randomized controlled trials most relevant to a given query. Building on prior work, the system retrieves trial publications matching a query specifying a combination of condition, intervention(s), and outcome(s), and ranks these according to sample size and estimated study quality. The top-k such studies are passed through a neural multi-document summarization system, yielding a synopsis of these trials. We consider two architectures: A standard sequence-to-sequence model based on BART and a multi-headed architecture intended to provide greater transparency to end-users. Both models produce fluent and relevant summaries of evidence retrieved for queries, but their tendency to introduce unsupported statements render them inappropriate for use in this domain at present. The proposed architecture may help users verify outputs allowing users to trace generated tokens back to inputs.
翻译:我们提出TrealsSummarizer, 这个系统旨在自动总结一组随机控制试验中提供的证据, 与特定查询最相关的证据。 以先前的工作为基础, 该系统检索了测试性出版物, 匹配一个询问, 具体说明条件、 干预和结果的组合, 并且根据抽样规模和估计研究质量排列这些出版物。 顶尖的这类研究通过神经多文件汇总系统通过, 产生这些试验的概要。 我们考虑了两个结构: 一个基于BART的标准序列至序列模型和一个旨在向最终用户提供更大透明度的多头结构。 两个模型都生成了为查询检索而检索的证据流畅和相关的摘要, 但是它们倾向于引入无根据的报表,因此目前不宜用于这一领域的用途。 拟议的结构可以帮助用户核实允许用户追踪生成的代号返回投入的产出。</s>